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

    Neuronpedia

    INDEX
    Explanations

    terms associated with categories or classifications in both narrative and technical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    缤
    -0.14
    ]++;↵
    -0.13
    Attached
    -0.13
    cestor
    -0.13
    imuth
    -0.13
    pectrum
    -0.13
    CHANNEL
    -0.13
    ì°¬
    -0.13
    äsent
    -0.13
    aware
    -0.13
    POSITIVE LOGITS
    dings
    0.19
    κÏĮ
    0.16
    orr
    0.16
    antly
    0.16
    committed
    0.15
     freely
    0.15
    onian
    0.15
    imos
    0.15
    leon
    0.15
    abo
    0.15
    Act Density 0.044%

    No Known Activations