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

    Neuronpedia

    INDEX
    Explanations

    terms related to frequency and preference in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    occo
    -0.19
    abet
    -0.17
    _charset
    -0.15
    .Restrict
    -0.14
    positor
    -0.14
    hack
    -0.14
     Circular
    -0.14
     hack
    -0.14
    BufferSize
    -0.14
    undry
    -0.14
    POSITIVE LOGITS
     mic
    0.18
     micro
    0.17
     MICRO
    0.17
    arts
    0.17
     impressions
    0.17
    Mic
    0.17
     Mic
    0.17
    micro
    0.16
    mic
    0.16
     Micro
    0.15
    Act Density 0.014%

    No Known Activations