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

    Neuronpedia

    INDEX
    Explanations

    non-specific contextual phrases that indicate an event or action occurring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ActionTypes
    -0.18
     Davidson
    -0.16
     Merrill
    -0.15
     Q
    -0.14
     Sala
    -0.14
    ifica
    -0.14
     selector
    -0.14
     soma
    -0.14
    oday
    -0.14
     Tod
    -0.14
    POSITIVE LOGITS
     Blo
    0.16
    #
    0.16
    Blo
    0.15
    onis
    0.15
    _Tis
    0.15
    Äħż
    0.15
    اÙĨس
    0.14
    .Toolkit
    0.14
    peat
    0.14
    iosper
    0.14
    Act Density 0.001%

    No Known Activations