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

    Neuronpedia

    INDEX
    Explanations

    qualifiers that intensify or modify adjectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.63
     officinalis
    -0.61
     espere
    -0.56
    RenderAtEndOf
    -0.55
     dolorosa
    -0.55
    IntoConstraints
    -0.54
     Yarmouth
    -0.54
     futuro
    -0.53
     azzurro
    -0.53
     magari
    -0.53
    POSITIVE LOGITS
     easier
    0.72
     enough
    0.68
    Искәрмәләр
    0.62
    GINS
    0.61
    夠
    0.60
     easy
    0.60
    valent
    0.60
    hlander
    0.58
    nicity
    0.57
     compared
    0.57
    Act Density 0.251%

    No Known Activations