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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases starting with "If"

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or hypotheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ãĥŃ
    -0.70
    iliar
    -0.68
    %);
    -0.67
    FTWARE
    -0.64
    ãĤª
    -0.61
    Rated
    -0.60
     Deity
    -0.60
    DAQ
    -0.60
    emetery
    -0.59
    âĵĺ
    -0.59
    POSITIVE LOGITS
    fy
    0.87
    rame
    0.86
     you
    0.84
    yip
    0.81
     unchecked
    0.78
     anything
    0.72
    ihad
    0.71
    tar
    0.66
     somebody
    0.65
    soever
    0.63
    Act Density 0.103%

    No Known Activations