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

    Neuronpedia

    INDEX
    Explanations

    the word "ant" in different contexts

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the substring "ant" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    UTION
    -0.86
    MET
    -0.75
    earchers
    -0.74
    STON
    -0.73
    çīĪ
    -0.71
    ftime
    -0.68
    displayText
    -0.68
    soDeliveryDate
    -0.68
    ¯¯¯¯¯¯¯¯
    -0.68
    TOR
    -0.68
    POSITIVE LOGITS
    ucket
    1.08
    heon
    1.04
    anamo
    0.97
    ean
    0.91
    rell
    0.91
    ropy
    0.90
    ech
    0.89
    asma
    0.88
    ioch
    0.87
    iary
    0.87
    Act Density 0.056%

    No Known Activations