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

    Neuronpedia

    INDEX
    Explanations

    phrases related to meeting someone or achieving a goal

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships and connections between people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     untreated
    -0.67
    taboola
    -0.61
     redistributed
    -0.61
    uploads
    -0.61
     sake
    -0.60
     collects
    -0.60
     phased
    -0.59
    icides
    -0.59
     affecting
    -0.57
     escaped
    -0.57
    POSITIVE LOGITS
     halfway
    0.93
    lyak
    0.85
    tle
    0.77
     expectations
    0.74
    ritic
    0.73
     requirements
    0.68
    zeb
    0.68
    ilaterally
    0.67
    zb
    0.66
     criterion
    0.66
    Act Density 0.119%

    No Known Activations