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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "recuse" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    words related to the concept of "using" or "reusing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blumenthal
    -0.77
    icky
    -0.67
    minecraft
    -0.67
    belt
    -0.64
    laden
    -0.61
    alone
    -0.60
    bags
    -0.60
    bridge
    -0.60
     Bj
    -0.59
     knot
    -0.58
    POSITIVE LOGITS
    rocal
    0.93
     ACTIONS
    0.91
    ctions
    0.88
    owship
    0.87
    tions
    0.87
    atorium
    0.84
    llor
    0.82
    anz
    0.82
    issance
    0.82
    ction
    0.79
    Act Density 0.044%

    No Known Activations