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

    Neuronpedia

    INDEX
    Explanations

    negations or phrases that express the absence of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ertoire
    -0.16
    uffman
    -0.15
    lish
    -0.15
    riere
    -0.15
    ramer
    -0.15
    flen
    -0.15
    buster
    -0.15
    rière
    -0.14
    thon
    -0.14
    adors
    -0.14
    POSITIVE LOGITS
     throwable
    0.16
    ãĥ£
    0.15
     Malik
    0.14
    αλλ
    0.14
    _axes
    0.14
     Uns
    0.13
    uka
    0.13
    _pkt
    0.13
     Fore
    0.13
    pkt
    0.13
    Act Density 0.042%

    No Known Activations