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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "Ir" and variations of it, highlighting a particular name or identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.21
    ilded
    -0.20
     evil
    -0.16
    omic
    -0.16
    icious
    -0.16
    CRY
    -0.15
    lý
    -0.15
    abet
    -0.15
    ears
    -0.15
    alth
    -0.15
    POSITIVE LOGITS
    replace
    0.23
    regular
    0.22
    ritable
    0.21
    ving
    0.21
     Ir
    0.20
    win
    0.20
    ises
    0.19
    relevant
    0.19
    ration
    0.19
     ir
    0.19
    Act Density 0.016%

    No Known Activations