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

    Neuronpedia

    INDEX
    Explanations

    conditional and speculative phrases

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

    Code or data snippets

    np_acts-logits-general · gemini-2.0-flash

    if you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    herself
    -0.76
    our
    -0.66
     ourselves
    -0.65
    his
    -0.62
    OUR
    -0.61
     Your
    -0.60
     hans
    -0.60
     herself
    -0.59
     mich
    -0.59
    himself
    -0.59
    POSITIVE LOGITS
     autorytatywna
    1.15
     ujednoznacz
    1.13
    ValueStyle
    1.10
    Datuak
    1.06
     EconPapers
    1.04
    帖最后由
    1.01
     esternos
    0.99
    tvguidetime
    0.98
     @"/
    0.96
    \{\\
    0.95
    Act Density 0.761%

    No Known Activations