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

    Neuronpedia

    INDEX
    Explanations

    technical terms related to data management and web development

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to system operations and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Aven
    -0.69
     Barron
    -0.69
     Flavoring
    -0.68
     juven
    -0.68
     Lank
    -0.66
     lawy
    -0.63
    Ùħ
    -0.63
     Moe
    -0.61
     Streets
    -0.60
     Gors
    -0.59
    POSITIVE LOGITS
    able
    1.54
    ability
    1.24
    ables
    1.22
    er
    1.20
    ment
    1.11
    ers
    1.10
    ername
    0.98
    ABLE
    0.96
     button
    0.96
    ation
    0.94
    Act Density 0.240%

    No Known Activations