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

    Neuronpedia

    INDEX
    Explanations

    evidence or actions related to investigations or legal matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating possession or confirmation of actions or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ][/
    -0.79
    adelphia
    -0.79
    gery
    -0.78
    ggles
    -0.76
    tale
    -0.74
    geries
    -0.74
    fter
    -0.71
     Fey
    -0.69
    eah
    -0.68
    iques
    -0.67
    POSITIVE LOGITS
     predecessor
    0.77
     neighbour
    0.74
     raining
    0.72
     reorgan
    0.70
     abolish
    0.67
     annex
    0.67
     rivals
    0.66
     operational
    0.64
     itself
    0.63
     reserves
    0.63
    Act Density 0.394%

    No Known Activations