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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     NUKAT
    -0.68
    🔥🔥
    -0.65
     AssemblyCulture
    -0.63
    zeba
    -0.63
    Marcia
    -0.63
    principalTable
    -0.63
    rrggbb
    -0.62
    vola
    -0.61
     wikipagina
    -0.61
    󠁢
    -0.60
    POSITIVE LOGITS
    Though
    0.96
    While
    0.88
    Although
    0.88
     Though
    0.88
     While
    0.83
    though
    0.82
     though
    0.81
     Although
    0.79
    Meski
    0.72
    Whilst
    0.71
    Act Density 0.126%

    No Known Activations