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

    Neuronpedia

    INDEX
    Explanations

    mentions of blockbuster movies

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific theatrical production or performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ippers
    -0.81
    emonic
    -0.72
     Defenders
    -0.72
    uckland
    -0.72
    enium
    -0.71
    immer
    -0.69
    tern
    -0.67
    akings
    -0.67
    orian
    -0.66
    orians
    -0.65
    POSITIVE LOGITS
     touches
    0.64
    aceous
    0.64
     reinforcement
    0.62
     RH
    0.61
     handc
    0.61
     coating
    0.61
    OLOGY
    0.60
     srf
    0.60
     syll
    0.59
     till
    0.59
    Act Density 0.000%

    No Known Activations