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

    Neuronpedia

    INDEX
    Explanations

    phrasal expressions indicating sequences or consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    клопе
    -0.61
    AxisAlignment
    -0.56
    brities
    -0.56
    OWN
    -0.50
    usc
    -0.48
    roughs
    -0.48
    inkan
    -0.48
    resti
    -0.47
     rose
    -0.47
    ongan
    -0.46
    POSITIVE LOGITS
     CreateTagHelper
    0.57
     afterwards
    0.57
     afterward
    0.55
     accompanies
    0.55
    Datuak
    0.55
    Afterwards
    0.53
     NUKAT
    0.49
     wohin
    0.48
     autorytatywna
    0.48
    salms
    0.48
    Act Density 0.679%

    No Known Activations