Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    expressions of concern and inquiries related to personal experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to user concerns and inquiries about data security

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressed feelings and beliefs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Hentet
    -0.59
     Schme
    -0.45
     bene
    -0.45
     dependency
    -0.45
    Gön
    -0.44
    lotte
    -0.44
    Require
    -0.43
    ец
    -0.43
     Argu
    -0.43
     done
    -0.42
    POSITIVE LOGITS
     expressed
    0.76
    expressed
    0.75
     voiced
    0.69
    PerformLayout
    0.66
     exprim
    0.66
     Baillargeon
    0.65
     gehabt
    0.65
     express
    0.64
    CodeAttribute
    0.63
    SHARE
    0.63
    Act Density 0.154%

    No Known Activations