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

    Neuronpedia

    INDEX
    Explanations

    words and phrases that emphasize the concepts of names, contexts, and frameworks in relation to discussions or arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    jah
    -0.17
    å½
    -0.14
    azy
    -0.14
    æ·
    -0.14
     dagen
    -0.14
    ribly
    -0.14
     saja
    -0.13
    _Reference
    -0.13
    .bits
    -0.13
    à¹Ħว
    -0.13
    POSITIVE LOGITS
    est
    0.16
    .dis
    0.15
     Arch
    0.15
    /in
    0.15
    erring
    0.15
     DropIndex
    0.15
    677
    0.14
    otti
    0.14
    ósito
    0.14
    ture
    0.14
    Act Density 0.224%

    No Known Activations