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

    Neuronpedia

    INDEX
    Explanations

    names of individuals and positions in official capacities

    oai_token-act-pair · gpt-3.5-turbo

    names and job titles related to officials or authorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     equivalents
    -0.54
    tumblr
    -0.53
     undermin
    -0.52
     womb
    -0.48
     hereafter
    -0.48
     destro
    -0.48
     blah
    -0.46
     fulfillment
    -0.46
    ividual
    -0.45
    gettable
    -0.45
    POSITIVE LOGITS
     (@
    0.65
    án
    0.62
    jit
    0.59
    agy
    0.59
    avan
    0.58
    ás
    0.58
    berto
    0.57
    anton
    0.57
    ima
    0.56
    ofer
    0.56
    Act Density 0.480%

    No Known Activations