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

    Neuronpedia

    INDEX
    Explanations

    verbs related to actions or activities

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to ongoing actions or efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eka
    -0.70
    Ver
    -0.63
    anka
    -0.63
    aterasu
    -0.61
    ku
    -0.61
    ember
    -0.59
    aurus
    -0.59
    kb
    -0.58
    rust
    -0.58
    allas
    -0.58
    POSITIVE LOGITS
     lately
    1.04
    issance
    0.80
     downhill
    0.77
     awhile
    0.76
     steadily
    0.74
     since
    0.73
     agitation
    0.69
    leground
    0.68
     largeDownload
    0.66
     indefinitely
    0.66
    Act Density 0.114%

    No Known Activations