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

    Neuronpedia

    INDEX
    Explanations

    quantitative assessments of interventions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    unction
    -1.54
     assumption
    -1.49
    ]=
    -1.44
    ubation
    -1.38
    TE
    -1.37
     conjugation
    -1.36
    ÃŁe
    -1.35
    unnumbered
    -1.33
    ncia
    -1.33
    )\|_{
    -1.33
    POSITIVE LOGITS
     shooter
    1.67
     featured
    1.55
     fireplace
    1.53
     magazines
    1.52
     strikes
    1.50
    istically
    1.50
     native
    1.47
     paradise
    1.44
     poster
    1.44
    !(
    1.43
    Act Density 0.354%

    No Known Activations