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

    Neuronpedia

    INDEX
    Explanations

    the word "ant" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     conse
    -0.54
     fale
    -0.54
    pital
    -0.49
    Geplaatst
    -0.49
     Doble
    -0.48
     Titi
    -0.47
     kicking
    -0.47
     Pura
    -0.47
     facts
    -0.46
    ValueGenerated
    -0.46
    POSITIVE LOGITS
    ant
    2.06
     Ant
    1.55
     ant
    1.52
    Ant
    1.41
    ANT
    1.27
    __":
    0.88
     ANT
    0.84
    __':
    0.82
    antre
    0.81
    antro
    0.77
    Act Density 0.058%

    No Known Activations