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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating compatibility or suitability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nis
    -0.17
    że
    -0.15
    ServiceImpl
    -0.14
     нами
    -0.14
    kip
    -0.14
    енка
    -0.14
    ulla
    -0.13
    _mex
    -0.13
     Zi
    -0.13
    wen
    -0.13
    POSITIVE LOGITS
     into
    0.25
    into
    0.22
     Into
    0.21
    Into
    0.19
     perfectly
    0.19
     nicely
    0.18
    _into
    0.17
     within
    0.17
     vÃło
    0.17
     PERF
    0.17
    Act Density 0.057%

    No Known Activations