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

    Neuronpedia

    INDEX
    Explanations

    words related to incompleteness or uncertainty

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "in" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     warr
    -0.72
     Continued
    -0.71
    MORE
    -0.60
     Rabbit
    -0.60
     Tie
    -0.60
    Sov
    -0.60
     behavi
    -0.60
    Magikarp
    -0.60
     Strawberry
    -0.60
     laun
    -0.59
    POSITIVE LOGITS
    ciples
    0.97
    alg
    0.94
    arious
    0.94
    cially
    0.93
    ogens
    0.93
    ogenic
    0.92
    ements
    0.90
    cess
    0.90
    ogen
    0.89
    osaurs
    0.89
    Act Density 0.080%

    No Known Activations