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

    Neuronpedia

    INDEX
    Explanations

    phrases related to appearance or perception

    oai_token-act-pair · gpt-3.5-turbo

    phrases that discuss appearance or perception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ItemTracker
    -0.84
    ifles
    -0.73
    PsyNetMessage
    -0.71
     Bringing
    -0.71
    ettings
    -0.71
    ufact
    -0.70
    ordering
    -0.70
     Variant
    -0.69
     Introduced
    -0.66
    arius
    -0.65
    POSITIVE LOGITS
    vind
    0.85
     louder
    0.73
     unwelcome
    0.71
     stronger
    0.70
     smarter
    0.70
     weaker
    0.67
     invincible
    0.66
     uncomfortable
    0.66
    zynski
    0.66
     disappear
    0.66
    Act Density 0.065%

    No Known Activations