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

    Neuronpedia

    INDEX
    Explanations

    contractions and negative forms of auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    negative contractions (primarily "didn't", "wasn't", "hasn't", "wouldn't").

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Negative Logits
     lat
    -0.33
     sol
    -0.32
     pou
    -0.32
     civilisation
    -0.31
     mar
    -0.31
     Whilst
    -0.31
     prepared
    -0.31
    う
    -0.30
     amongst
    -0.29
     utilisation
    -0.29
    POSITIVE LOGITS
    Hentet
    0.75
     autorytatywna
    0.68
    GEBURTSDATUM
    0.65
    tagHelperRunner
    0.65
    berdayakan
    0.64
     pouvoit
    0.63
    Rhestr
    0.59
     Einleitung
    0.59
     auroit
    0.58
    EDEFAULT
    0.58
    Act Density 0.461%

    No Known Activations