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

    Neuronpedia

    INDEX
    Explanations

    connective phrases that indicate relationships or transitions between ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     ligiloj
    -0.93
    ſelf
    -0.81
    σθαι
    -0.79
     itſelf
    -0.76
     myſelf
    -0.73
     $_"
    -0.72
     Jefus
    -0.71
     pleaſure
    -0.71
     Majefty
    -0.71
     Monfieur
    -0.71
    POSITIVE LOGITS
    etc
    0.73
    Etc
    0.64
     etc
    0.61
     Etc
    0.57
     appunto
    0.54
    何より
    0.52
    /
    0.51
     surtout
    0.49
    And
    0.49
     /
    0.48
    Act Density 0.164%

    No Known Activations