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

    Neuronpedia

    INDEX
    Explanations

    references to emotional reactions or frustrations towards family and personal relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    .localization
    -0.07
    /validation
    -0.07
    icamente
    -0.07
    ifo
    -0.07
    _usec
    -0.07
    обов
    -0.07
    ieber
    -0.07
    ietet
    -0.07
     baiser
    -0.06
    inki
    -0.06
    POSITIVE LOGITS
     surprise
    0.08
     pur
    0.07
    pur
    0.07
     shadow
    0.06
     greatly
    0.06
    TabIndex
    0.06
     repeat
    0.06
     faithful
    0.06
     contrast
    0.06
     extreme
    0.06
    Act Density 0.006%

    No Known Activations