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

    Neuronpedia

    INDEX
    Explanations

    action verbs related to tasks or activities

    oai_token-act-pair · gpt-3.5-turbo

    references to actions or tasks that are being done or completed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    iary
    -0.73
    awar
    -0.70
     indictment
    -0.64
    noon
    -0.61
    BILITY
    -0.61
    ISSION
    -0.61
    CVE
    -0.60
    iche
    -0.60
    ICO
    -0.59
    ANCE
    -0.59
    POSITIVE LOGITS
     happening
    0.90
     differently
    0.89
     toget
    0.88
     happen
    0.83
     happ
    0.81
     happened
    0.79
     else
    0.75
    selves
    0.74
    cale
    0.73
    flows
    0.71
    Act Density 0.045%

    No Known Activations