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

    Neuronpedia

    INDEX
    Explanations

    references to blame or fault

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nessed
    -0.68
     ISTAT
    -0.68
     assoluto
    -0.67
    ngdoc
    -0.65
    voort
    -0.64
     محفوظة
    -0.63
     Hartman
    -0.63
     мәкал
    -0.63
    chemic
    -0.62
    SLS
    -0.62
    POSITIVE LOGITS
     fault
    1.17
     Fault
    1.03
    fault
    0.99
    Fault
    0.91
    FAULT
    0.69
     Liability
    0.67
    DOCTYPE
    0.65
     faute
    0.65
     idio
    0.65
     Diagrams
    0.64
    Act Density 0.061%

    No Known Activations