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

    Neuronpedia

    INDEX
    Explanations

    statements related to hypothetical scenarios or regrets

    oai_token-act-pair · gpt-3.5-turbo

    references to hypothetical scenarios and conditional statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    lies
    -0.65
    gae
    -0.62
    ilial
    -0.61
    */(
    -0.59
     externalToEVAOnly
    -0.57
     braces
    -0.57
     nutshell
    -0.55
    DX
    -0.54
    ãĥ¯
    -0.53
    inates
    -0.53
    POSITIVE LOGITS
    would
    1.65
     would
    1.54
     wouldn
    1.45
     Would
    1.45
    Would
    1.27
     Wouldn
    1.19
    'd
    1.13
    could
    1.05
     could
    0.93
    OULD
    0.90
    Act Density 0.630%

    No Known Activations