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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to collaboration and productivity

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "work" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Flavoring
    -0.84
     Augustus
    -0.69
     juven
    -0.62
     Bubble
    -0.62
     gratification
    -0.61
    anga
    -0.61
    famous
    -0.60
     Revel
    -0.60
    gow
    -0.60
    anamo
    -0.59
    POSITIVE LOGITS
    fare
    1.02
     collabor
    1.00
    hops
    0.98
    bench
    0.97
     tirelessly
    0.89
     ethic
    0.87
    forces
    0.87
    heet
    0.84
    ington
    0.82
     toward
    0.79
    Act Density 0.075%

    No Known Activations