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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or behaviors

    oai_token-act-pair · gpt-3.5-turbo

    verbs that express actions, thoughts, or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Reviewer
    -0.92
    umption
    -0.70
    ornia
    -0.63
     Kam
    -0.62
     Tad
    -0.61
     Bryce
    -0.61
    ember
    -0.60
     Chang
    -0.59
    ubi
    -0.59
    isSpecialOrderable
    -0.58
    POSITIVE LOGITS
     Attention
    0.70
     PsyNet
    0.65
    prus
    0.61
     lipid
    0.61
    ophobic
    0.59
    zbollah
    0.58
     signals
    0.57
    ono
    0.57
    ropri
    0.55
     Piercing
    0.55
    Act Density 0.258%

    No Known Activations