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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "come" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ikip
    -0.17
    foy
    -0.16
    ubi
    -0.16
    rit
    -0.15
    tright
    -0.15
    lops
    -0.14
    bih
    -0.14
    rible
    -0.14
    eldorf
    -0.14
    jure
    -0.14
    POSITIVE LOGITS
    upp
    0.23
     forward
    0.22
     into
    0.22
    plete
    0.21
    backs
    0.21
    leon
    0.19
     forth
    0.19
    pletely
    0.19
     to
    0.18
     back
    0.17
    Act Density 0.056%

    No Known Activations