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

    Neuronpedia

    INDEX
    Explanations

    instances referring to conditions or stipulations for permission or approval

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating conditional statements or requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ictionary
    -0.88
    hack
    -0.75
    isal
    -0.74
    ivot
    -0.72
    MpServer
    -0.71
     Worse
    -0.71
    leon
    -0.70
    ãĥ¼ãĥĨ
    -0.70
    esi
    -0.70
    lez
    -0.68
    POSITIVE LOGITS
     they
    0.90
     nobody
    0.87
     THEY
    0.85
     there
    0.84
     you
    0.82
     thou
    0.76
     practicable
    0.74
     respecting
    0.73
     conditions
    0.72
     neither
    0.72
    Act Density 0.082%

    No Known Activations