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

    Neuronpedia

    INDEX
    Explanations

    instances of current actions related to training or preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    sidemargin
    -0.63
     auroit
    -0.60
     resourceCulture
    -0.57
    httphttps
    -0.54
    abestanden
    -0.52
    Heres
    -0.52
     كومونز
    -0.51
    chtenstein
    -0.50
     eût
    -0.49
    albeit
    -0.49
    POSITIVE LOGITS
     maybe
    0.49
     arrive
    0.44
     tomorrow
    0.44
     stupid
    0.42
     sleeping
    0.42
     provocation
    0.42
     unbelievable
    0.41
     dreaming
    0.41
     arrived
    0.41
     cannot
    0.41
    Act Density 0.142%

    No Known Activations