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
    dzi
    -0.16
    rit
    -0.16
    ume
    -0.15
    forme
    -0.15
    iei
    -0.15
     infer
    -0.15
    amac
    -0.14
    ritz
    -0.14
    licer
    -0.14
    urai
    -0.14
    POSITIVE LOGITS
     back
    0.21
     here
    0.19
     home
    0.18
    upp
    0.17
     into
    0.17
    backs
    0.16
    _here
    0.16
     onto
    0.16
    -back
    0.16
    here
    0.15
    Act Density 0.052%

    No Known Activations