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

    Neuronpedia

    INDEX
    Explanations

    phrases related to personal growth and improvement

    oai_token-act-pair · gpt-3.5-turbo

    phrases and expressions that indicate positive outcomes or benefits

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Bloom
    -0.68
    Reviewed
    -0.64
     backdrop
    -0.63
     Trident
    -0.63
    Lot
    -0.61
     Artemis
    -0.61
     Affect
    -0.61
    Netflix
    -0.60
     itself
    -0.60
     Framework
    -0.59
    POSITIVE LOGITS
    oké
    0.75
    arest
    0.72
    inki
    0.69
    friend
    0.69
    wagen
    0.68
    isner
    0.66
    onz
    0.64
    iership
    0.64
    rower
    0.63
    cffff
    0.62
    Act Density 0.448%

    No Known Activations