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

    Neuronpedia

    INDEX
    Explanations

    references to interviews and discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orget
    -0.15
    Ñĸла
    -0.15
    erosis
    -0.15
    OrNull
    -0.15
    olie
    -0.15
    }elseif
    -0.14
    querque
    -0.14
    ANN
    -0.13
    agram
    -0.13
     htons
    -0.13
    POSITIVE LOGITS
     interview
    0.79
     Interview
    0.70
     interviews
    0.66
     interviewed
    0.62
    Interview
    0.61
     entrev
    0.61
     Interviews
    0.57
     interviewer
    0.57
     interviewing
    0.47
    erview
    0.38
    Act Density 0.254%

    No Known Activations