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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a conclusion or cessation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    澤
    -0.16
    761
    -0.16
     friendly
    -0.16
    Friendly
    -0.16
    zl
    -0.15
    .appspot
    -0.14
    anders
    -0.14
    gressor
    -0.14
    Bindings
    -0.14
    _DUMP
    -0.14
    POSITIVE LOGITS
    orse
    0.17
    dorf
    0.15
    uja
    0.15
    plat
    0.14
    cai
    0.14
    .cv
    0.14
     SAP
    0.13
     èĻ
    0.13
    aryl
    0.13
    em
    0.13
    Act Density 0.077%

    No Known Activations