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

    Neuronpedia

    INDEX
    Explanations

    phrases related to investigation or crime-related contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -0.91
     avoient
    -0.90
     Monfieur
    -0.88
     himſelf
    -0.88
     aveug
    -0.85
    berdayakan
    -0.85
     themſelves
    -0.84
     quelcon
    -0.83
     itſelf
    -0.83
     varandra
    -0.83
    POSITIVE LOGITS
    ⓧ
    0.93
     final
    0.67
     s
    0.63
    ее
    0.61
    __.__
    0.61
    みの
    0.57
     ur
    0.56
     its
    0.55
    "]').
    0.55
     last
    0.55
    Act Density 0.044%

    No Known Activations