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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to work or performance

    oai_token-act-pair · gpt-3.5-turbo

    verbs related to participation or involvement in activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     forgetting
    -0.80
    uyomi
    -0.79
    pmwiki
    -0.74
    catentry
    -0.74
     wont
    -0.69
    quickShipAvailable
    -0.67
     Explosion
    -0.66
    fortunately
    -0.64
    76561
    -0.63
     Bubble
    -0.62
    POSITIVE LOGITS
    dress
    0.79
    eport
    0.72
     alongside
    0.69
    heed
    0.69
     purposes
    0.67
     theirs
    0.67
    uke
    0.66
    enance
    0.64
    agine
    0.63
    cliffe
    0.63
    Act Density 0.348%

    No Known Activations