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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to behavior and attitudes

    oai_token-act-pair · gpt-3.5-turbo

    terms that relate to openness and accessibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unknown
    -0.67
    Strike
    -0.67
    CTV
    -0.65
    atel
    -0.64
    elf
    -0.64
    mol
    -0.64
    owell
    -0.64
    atch
    -0.63
    FORE
    -0.62
    adium
    -0.62
    POSITIVE LOGITS
     minded
    1.11
     than
    0.95
     sounding
    0.89
     paced
    0.85
    istic
    0.83
     agric
    0.82
     stance
    0.79
     approach
    0.78
    looking
    0.75
    idious
    0.74
    Act Density 0.281%

    No Known Activations