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

    Neuronpedia

    INDEX
    Explanations

    titles or references to different types of media

    oai_token-act-pair · gpt-3.5-turbo

    instances of a large variety of creatures or entities, often accompanied by descriptive elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     seism
    -0.79
     sidew
    -0.74
     ultr
    -0.72
     multif
    -0.69
     seismic
    -0.69
     deficient
    -0.68
     suspic
    -0.67
     petertodd
    -0.67
     ageing
    -0.67
     decentral
    -0.66
    POSITIVE LOGITS
     Known
    0.91
     Kills
    0.87
    lihood
    0.86
    Else
    0.84
     Things
    0.83
     Together
    0.83
     Limits
    0.82
     Pieces
    0.82
     Tomorrow
    0.82
     Married
    0.81
    Act Density 0.171%

    No Known Activations