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

    Neuronpedia

    INDEX
    Explanations

    the word "plus" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vgili
    -0.42
    Langue
    -0.38
    Voltaje
    -0.38
     Herder
    -0.35
     Authors
    -0.35
     Geruch
    -0.35
     Writers
    -0.35
    ://"
    -0.35
    gorit
    -0.34
     eukaryotic
    -0.34
    POSITIVE LOGITS
     plus
    1.63
    plus
    1.59
     Plus
    1.58
    Plus
    1.57
    PLUS
    1.42
     PLUS
    1.40
     плюс
    1.36
     ditambah
    0.98
     Minus
    0.96
    minus
    0.95
    Act Density 0.128%

    No Known Activations