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

    Neuronpedia

    INDEX
    Explanations

    expressions of personal accountability and reflection on relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    slaught
    -0.17
     ìŀĪëĬĶëį°
    -0.16
     Affero
    -0.15
     Guar
    -0.14
    #echo
    -0.14
    /framework
    -0.14
     Kostenlose
    -0.14
    mesinin
    -0.13
    .COM
    -0.13
    .Framework
    -0.13
    POSITIVE LOGITS
    æĽ¾
    0.25
     had
    0.20
     original
    0.17
     æĽ
    0.16
     haber
    0.16
    ané
    0.16
     originally
    0.16
     did
    0.16
     was
    0.15
    rit
    0.15
    Act Density 0.170%

    No Known Activations