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

    Neuronpedia

    INDEX
    Explanations

    occurrences of high frequency, attention-seeking words or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    stit
    -0.15
    jerne
    -0.14
    NEG
    -0.14
     Jeh
    -0.14
    earch
    -0.14
    ì¶Ķ
    -0.13
    estone
    -0.13
    åŃĿ
    -0.13
    oes
    -0.13
     experimentation
    -0.13
    POSITIVE LOGITS
    SharedPtr
    0.15
    iov
    0.15
    çĶ
    0.15
    lag
    0.15
    IDES
    0.15
    __,__
    0.15
    eya
    0.15
    unda
    0.15
    oute
    0.14
    eko
    0.14
    Act Density 0.009%

    No Known Activations