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

    Neuronpedia

    INDEX
    Explanations

    references to new experiences and beginner status in various contexts

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Negative Logits
    writeFieldEnd
    -0.61
    )}-\
    -0.54
    redacted
    -0.52
    newswire
    -0.49
    бет
    -0.48
    )}-
    -0.47
    ulisan
    -0.47
     separately
    -0.47
     close
    -0.47
    xtures
    -0.46
    POSITIVE LOGITS
     unskilled
    0.69
     Roskov
    0.64
    دانشنامهٔ
    0.63
    skill
    0.61
     createStore
    0.61
     skill
    0.59
     amateur
    0.58
     novices
    0.57
     beginner
    0.57
    初心者
    0.57
    Act Density 0.359%

    No Known Activations