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

    Neuronpedia

    INDEX
    Explanations

    suggestions or proposals

    oai_token-act-pair · gpt-3.5-turbo

    suggestions or proposals for alternative actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    oken
    -0.78
    ULTS
    -0.70
     sensing
    -0.66
    htaking
    -0.65
    ukemia
    -0.64
    omen
    -0.64
    ieth
    -0.62
     Winning
    -0.62
    20439
    -0.61
    ELD
    -0.61
    POSITIVE LOGITS
     postpone
    1.27
     ditch
    1.24
     automate
    1.20
     rethink
    1.18
     revert
    1.17
     concentrate
    1.17
     rename
    1.16
     try
    1.15
     simplify
    1.13
     borrow
    1.12
    Act Density 0.322%

    No Known Activations