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

    Neuronpedia

    INDEX
    Explanations

    instances of dialogue and punctuation indicating speech

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hei
    -0.15
    ighted
    -0.15
    kle
    -0.14
    prit
    -0.14
     lawful
    -0.13
    riot
    -0.13
    vida
    -0.13
    OWN
    -0.13
     saya
    -0.13
    iendo
    -0.13
    POSITIVE LOGITS
     behind
    0.19
    Inst
    0.19
     Gods
    0.18
     Inst
    0.18
     Relief
    0.17
     sweat
    0.17
     Normally
    0.17
     Pull
    0.16
    defgroup
    0.16
    tion
    0.15
    Act Density 0.265%

    No Known Activations