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

    Neuronpedia

    INDEX
    Explanations

    parts of the text that introduce a conditional statement

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĤª
    -0.73
    âĵĺ
    -0.71
    iliar
    -0.70
    ãĥŃ
    -0.67
    forth
    -0.66
    女
    -0.64
    FTWARE
    -0.64
    ãĥ£
    -0.64
    ãĥ´
    -0.62
    asis
    -0.61
    POSITIVE LOGITS
    fy
    0.93
     you
    0.92
    rame
    0.91
    yip
    0.78
    ihad
    0.76
     unchecked
    0.69
     anything
    0.69
     anyone
    0.66
     anybody
    0.65
    orce
    0.65
    Act Density 0.090%

    No Known Activations