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

    Neuronpedia

    INDEX
    Explanations

    concepts related to modeling and representation in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     am
    -0.54
     tanke
    -0.51
    ⋮
    -0.48
     use
    -0.47
    am
    -0.47
    hes
    -0.47
    an
    -0.46
    Brains
    -0.46
     F
    -0.46
    ;
    -0.45
    POSITIVE LOGITS
     captures
    0.88
     capturing
    0.87
    ThroughAttribute
    0.84
     conveys
    0.84
     conveying
    0.83
     crdi
    0.82
     depicting
    0.82
     defaultstate
    0.80
     InputDecoration
    0.79
     peindre
    0.78
    Act Density 0.672%

    No Known Activations