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

    Neuronpedia

    INDEX
    Explanations

    action verbs that denote strong or impactful actions

    oai_token-act-pair · gpt-3.5-turbo

    gerunds and present participles indicating actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    available
    -0.70
    eg
    -0.69
    peg
    -0.67
    oha
    -0.66
    û
    -0.66
    pdf
    -0.65
    Reply
    -0.63
    ana
    -0.62
    yon
    -0.62
    utch
    -0.62
    POSITIVE LOGITS
    ãĥ¥
    0.70
    =]
    0.61
     agents
    0.60
    arts
    0.59
    redients
    0.58
     agent
    0.57
     aliases
    0.57
    LESS
    0.57
     starvation
    0.56
     aside
    0.55
    Act Density 0.272%

    No Known Activations