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

    Neuronpedia

    INDEX
    Explanations

    verbs related to prompting or encouraging actions

    oai_token-act-pair · gpt-3.5-turbo

    actions that suggest encouragement or requirements for compliance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hattan
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.70
    catentry
    -0.69
    Attempts
    -0.68
    pmwiki
    -0.68
    dating
    -0.65
    grad
    -0.62
    Downloadha
    -0.60
    fortunately
    -0.59
     Celeb
    -0.58
    POSITIVE LOGITS
    enance
    0.92
    uate
    0.80
     theirs
    0.78
    dress
    0.72
    leeve
    0.71
    igate
    0.69
    itate
    0.68
     their
    0.68
    plane
    0.67
    heed
    0.66
    Act Density 0.341%

    No Known Activations