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

    Neuronpedia

    INDEX
    Explanations

    modal verbs expressing obligation, suggestion, or prediction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Blech
    -0.52
    ismet
    -0.47
    τέλε
    -0.46
     affaire
    -0.46
    دل
    -0.46
    our
    -0.44
    وارد
    -0.43
     parem
    -0.43
    capi
    -0.42
    tikum
    -0.42
    POSITIVE LOGITS
     himself
    1.46
    himself
    1.13
     Himself
    1.13
     his
    0.92
    SizeF
    0.88
    因为他
    0.84
    His
    0.81
     Audiodateien
    0.79
    的他
    0.77
    AndEndTag
    0.77
    Act Density 0.190%

    No Known Activations