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

    Neuronpedia

    INDEX
    Explanations

    phrases related to face-to-face interactions

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to confrontations or interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    fml
    -0.86
    iston
    -0.79
    estones
    -0.74
    ortunate
    -0.74
    ancies
    -0.73
    roups
    -0.73
    ecause
    -0.70
    erest
    -0.67
    req
    -0.67
    redit
    -0.66
    POSITIVE LOGITS
    pal
    0.81
    ciating
    0.76
     unbeliev
    0.68
    ãĥ¼ãĥ
    0.64
     adversity
    0.63
     backdrop
    0.61
     danger
    0.60
    osaurus
    0.58
     Rath
    0.58
    Tur
    0.57
    Act Density 0.107%

    No Known Activations