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

    Neuronpedia

    INDEX
    Explanations

    active verbs expressing actions or contributions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ſelves
    -0.55
     reconstituted
    -0.54
     Houſe
    -0.53
     utafitiHapana
    -0.52
     Monfieur
    -0.51
     ingeniero
    -0.51
     damska
    -0.51
     Jefus
    -0.50
     myſelf
    -0.50
    labus
    -0.49
    POSITIVE LOGITS
    руя
    0.79
     thereby
    0.77
     thus
    0.75
     giving
    0.75
    giving
    0.72
    Dabei
    0.66
     кӀ
    0.66
    tagext
    0.63
     mostrando
    0.62
     favoring
    0.61
    Act Density 0.296%

    No Known Activations