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

    Neuronpedia

    INDEX
    Explanations

    references to specific topics or subjects in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     reasons
    -0.70
    ConstraintMaker
    -0.69
     ways
    -0.69
     redenen
    -0.65
    ंदीखरीदारी
    -0.61
     arguments
    -0.60
     ragioni
    -0.59
     signs
    -0.59
     Reasons
    -0.58
     Gründe
    -0.58
    POSITIVE LOGITS
     particular
    1.18
    particular
    0.97
     wonderful
    0.86
     amazing
    0.84
     incredible
    0.79
     latest
    0.76
     kind
    0.75
     important
    0.74
     lovely
    0.73
     sort
    0.72
    Act Density 0.385%

    No Known Activations