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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or speculation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of skepticism or uncertainty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    idelines
    -0.74
    elight
    -0.72
    thinkable
    -0.71
    perty
    -0.68
    bard
    -0.66
    taboola
    -0.66
    ierrez
    -0.64
    arantine
    -0.64
    ente
    -0.64
    ils
    -0.63
    POSITIVE LOGITS
    poke
    0.78
     paraph
    0.69
     anecd
    0.65
     Vlad
    0.63
     Rasmussen
    0.63
     CCP
    0.62
     readers
    0.61
    rh
    0.60
    NRS
    0.59
     myself
    0.57
    Act Density 0.159%

    No Known Activations