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

    Neuronpedia

    INDEX
    Explanations

    verbs related to causing actions or consequences

    oai_token-act-pair · gpt-3.5-turbo

    actions that suggest significant outcomes or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    onian
    -0.66
    jan
    -0.64
    luaj
    -0.62
     beware
    -0.61
     lately
    -0.61
    inis
    -0.61
    oqu
    -0.60
    ovie
    -0.60
    >>\
    -0.59
    yd
    -0.58
    POSITIVE LOGITS
     significantly
    0.81
     substantially
    0.79
     considerably
    0.77
    enance
    0.74
     future
    0.73
     greatly
    0.72
     untold
    0.71
     some
    0.71
     millions
    0.70
     further
    0.69
    Act Density 0.245%

    No Known Activations