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

    Neuronpedia

    INDEX
    Explanations

    requests or commands directed at someone

    oai_token-act-pair · gpt-3.5-turbo

    commands or requests involving actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    assic
    -0.74
    industrial
    -0.67
    fortunately
    -0.66
     guiActiveUnfocused
    -0.66
    etheless
    -0.66
     littered
    -0.66
    etimes
    -0.65
    EStreamFrame
    -0.64
     Detected
    -0.63
    catentry
    -0.62
    POSITIVE LOGITS
    enance
    0.88
    igate
    0.80
    escription
    0.75
    ance
    0.71
    uate
    0.70
    dress
    0.69
     seiz
    0.69
     restraint
    0.69
    ATIVE
    0.67
     him
    0.67
    Act Density 0.431%

    No Known Activations