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

    Neuronpedia

    INDEX
    Explanations

    references to items that can be found in a pocket

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pocket."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ANGEL
    -0.99
    ————————————————
    -0.80
    Reviewer
    -0.72
    rd
    -0.71
    EMENT
    -0.68
    actionDate
    -0.68
    SPA
    -0.65
    DEF
    -0.65
    mberg
    -0.64
    âĺħâĺħ
    -0.63
    POSITIVE LOGITS
    knife
    1.20
    book
    0.92
    notes
    0.91
    books
    0.88
    wallet
    0.87
    pocket
    0.81
    clip
    0.81
    watch
    0.79
    tex
    0.78
     pocket
    0.76
    Act Density 0.039%

    No Known Activations