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

    Neuronpedia

    INDEX
    Explanations

    phrases related to filling positions or gaps

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    eph
    -0.17
    ollection
    -0.16
    ÙĪÙĨÛĮ
    -0.15
    ieg
    -0.14
    usan
    -0.14
    isl
    -0.14
    ÙĪÛĮÛĮ
    -0.14
    culo
    -0.14
    RON
    -0.14
    isle
    -0.14
    POSITIVE LOGITS
    pie
    0.18
    itre
    0.16
     fill
    0.16
    prung
    0.15
    fill
    0.15
     pie
    0.15
     Fill
    0.14
    .restore
    0.14
    å¡«
    0.14
     filled
    0.14
    Act Density 0.037%

    No Known Activations