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

    Neuronpedia

    INDEX
    Explanations

    instances where communication or conversations are happening, specifically with the word 'with' before the entity being interacted with

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "speak with."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fighter
    -0.79
    ©¶æ¥µ
    -0.72
    waters
    -0.71
    ulo
    -0.68
    gross
    -0.65
    wikipedia
    -0.64
    chart
    -0.63
    mol
    -0.63
    anski
    -0.63
    works
    -0.62
    POSITIVE LOGITS
     regards
    1.11
     regard
    1.03
     strangers
    0.89
     passers
    0.85
     Samantha
    0.84
     representatives
    0.84
     coworkers
    0.83
    stood
    0.82
     fellow
    0.80
     constituents
    0.78
    Act Density 0.102%

    No Known Activations