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

    Neuronpedia

    INDEX
    Explanations

    verbs related to future actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate future intentions or plans

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ullah
    -0.79
     Horus
    -0.68
    ament
    -0.67
    heim
    -0.65
    aments
    -0.65
    ifle
    -0.64
    icone
    -0.64
    cluding
    -0.61
    sector
    -0.61
    picking
    -0.60
    POSITIVE LOGITS
    Ń·
    0.82
    verning
    0.78
    0.75
    -+
    0.72
    ãĥ£
    0.72
    ¸
    0.71
    lems
    0.70
    ggle
    0.70
     overboard
    0.68
    -|
    0.68
    Act Density 0.056%

    No Known Activations