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

    Neuronpedia

    INDEX
    Explanations

    time-related actions or events

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to the progression or conclusion of events over time

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥ¢
    -0.72
     kidding
    -0.71
    #$#$
    -0.68
    actly
    -0.62
    unless
    -0.59
    ãĤ±
    -0.58
     altogether
    -0.58
    èĢħ
    -0.56
    ################################
    -0.56
    discrimination
    -0.56
    POSITIVE LOGITS
     nearer
    1.07
     closer
    1.02
     deeper
    0.89
     increasingly
    0.86
     wealthier
    0.85
     richer
    0.84
     tighter
    0.82
     farther
    0.79
     thinner
    0.76
     colder
    0.76
    Act Density 0.111%

    No Known Activations