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

    Neuronpedia

    INDEX
    Explanations

    references to social media

    oai_token-act-pair · gpt-3.5-turbo

    mentions of social media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nces
    -0.90
     Cursed
    -0.83
    ñ
    -0.78
     Lank
    -0.75
    gger
    -0.71
    xual
    -0.71
    nce
    -0.70
    wered
    -0.70
    eters
    -0.69
    iasis
    -0.69
    POSITIVE LOGITS
     relations
    0.86
     cohesion
    0.84
     psychologists
    0.81
     psychologist
    0.80
     networking
    0.79
     norms
    0.79
     behavi
    0.79
     psychology
    0.76
     cues
    0.74
     welf
    0.74
    Act Density 0.025%

    No Known Activations