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

    Neuronpedia

    INDEX
    Explanations

    phrases related to calculation or probabilities in contexts involving discrete selections or combinations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     myſelf
    -1.91
     Monfieur
    -1.82
     itſelf
    -1.77
     Efq
    -1.76
     Jefus
    -1.74
     themſelves
    -1.72
     whoſe
    -1.61
     himſelf
    -1.60
    ſelves
    -1.54
     ―――――
    -1.52
    POSITIVE LOGITS
     pro
    0.76
     di
    0.71
     se
    0.66
     c
    0.63
     co
    0.62
     qu
    0.61
     le
    0.61
     a
    0.61
     f
    0.60
     d
    0.59
    Act Density 0.446%

    No Known Activations