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

    Neuronpedia

    INDEX
    Explanations

    hypothetical scenarios or situations

    oai_token-act-pair · gpt-3.5-turbo

    references to hypothetical or imaginary scenarios and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     largeDownload
    -0.93
    artney
    -0.88
    lain
    -0.81
    hani
    -0.79
    aina
    -0.78
    orie
    -0.78
    yer
    -0.77
    rix
    -0.76
    ieri
    -0.75
    iffs
    -0.75
    POSITIVE LOGITS
     hypot
    0.99
     hypothetical
    0.85
     aspir
    0.76
     bubble
    0.74
     extrap
    0.69
     feas
    0.68
     scenarios
    0.68
     whims
    0.68
     schizophren
    0.67
     mortal
    0.67
    Act Density 0.018%

    No Known Activations