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

    Neuronpedia

    INDEX
    Explanations

    sentences with phrases that indicate combining or adding elements together

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating combinations or additions of factors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fit
    -0.71
    idential
    -0.69
    ANS
    -0.69
    arest
    -0.69
    scribe
    -0.68
    ciation
    -0.67
    endant
    -0.66
    acement
    -0.66
    gered
    -0.65
    anos
    -0.65
    POSITIVE LOGITS
     fact
    0.81
     inexper
    0.79
     incompetence
    0.77
     sheer
    0.76
     paranoia
    0.72
     myriad
    0.70
     uncertainties
    0.69
     heightened
    0.68
     juggling
    0.67
     assorted
    0.67
    Act Density 0.188%

    No Known Activations