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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate reasons or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    DE
    -0.67
    heed
    -0.66
    iability
    -0.65
    illard
    -0.59
    odge
    -0.59
    fecture
    -0.59
    oos
    -0.58
     fraternity
    -0.58
    oir
    -0.58
     arrival
    -0.58
    POSITIVE LOGITS
     ranging
    1.06
     unspecified
    0.94
     unimaginable
    0.93
     resembling
    0.91
     unknown
    0.90
    ranging
    0.90
     pertaining
    0.89
     unrelated
    0.85
    afety
    0.85
    hift
    0.82
    Act Density 0.055%

    No Known Activations