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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progression or advancement in a person's life or career

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to movement or transition, particularly in relation to coming out of situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     authorizing
    -0.70
     distinguishing
    -0.69
     defining
    -0.69
     grouping
    -0.68
     referring
    -0.67
     treating
    -0.66
     demonstrating
    -0.66
     guaranteeing
    -0.66
     contacting
    -0.65
     telling
    -0.65
    POSITIVE LOGITS
    iped
    0.82
    edge
    0.76
    redients
    0.72
    icate
    0.72
    aughs
    0.71
    thood
    0.70
    olitical
    0.69
     Curve
    0.69
    unks
    0.67
    ilts
    0.65
    Act Density 0.806%

    No Known Activations