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

    Neuronpedia

    INDEX
    Explanations

    references to the concept of "share", typically indicating a portion or percentage of something

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "share" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    anwhile
    -0.86
     reper
    -0.80
    iasm
    -0.74
     skelet
    -0.70
    interrupted
    -0.69
     compr
    -0.69
     streng
    -0.68
    HCR
    -0.68
     tempor
    -0.67
     destro
    -0.62
    POSITIVE LOGITS
    cro
    1.29
    holder
    1.07
    holding
    1.04
    holders
    0.99
    ership
    0.98
    hold
    0.88
    hare
    0.87
    azo
    0.84
    busters
    0.80
    ability
    0.79
    Act Density 0.033%

    No Known Activations