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

    Neuronpedia

    INDEX
    Explanations

    terms related to thresholds in a technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    o
    -0.61
    a
    -0.55
    l
    -0.53
    e
    -0.53
    i
    -0.51
     Eins
    -0.50
    na
    -0.50
    ind
    -0.49
    い
    -0.48
    y
    -0.47
    POSITIVE LOGITS
     ritual
    1.05
    ritual
    1.05
     protocols
    0.94
     rituals
    0.94
     Protocols
    0.94
    featureID
    0.94
    principalTable
    0.93
    })*/
    0.91
     Ritual
    0.91
    };*/
    0.88
    Act Density 0.082%

    No Known Activations