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

    Neuronpedia

    INDEX
    Explanations

    sections related to toxicity and dosage in safety assessment contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     
    -0.55
     I
    -0.55
    2
    -0.54
    1
    -0.54
    -
    -0.53
    ,
    -0.53
     we
    -0.53
    !
    -0.51
    ’
    -0.50
    3
    -0.49
    POSITIVE LOGITS
     myſelf
    1.01
    Tikang
    1.01
     itſelf
    0.94
     Majefty
    0.93
     photolibrary
    0.92
     Савезне
    0.91
    脚注の使い方
    0.91
    ſelf
    0.90
     Waray
    0.88
     Roskov
    0.87
    Act Density 0.056%

    No Known Activations