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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases or statements using the word "if"

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and uncertainties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ouses
    -0.88
    itiz
    -0.88
    verts
    -0.86
    anners
    -0.80
    asonry
    -0.77
    stones
    -0.76
    ees
    -0.76
    EMENT
    -0.75
    eteen
    -0.74
    rients
    -0.74
    POSITIVE LOGITS
     somewhat
    0.98
     unsuccessful
    0.93
     unintentional
    0.91
     inaccurate
    0.90
     contradictory
    0.89
     unsuccessfully
    0.88
     admittedly
    0.87
     unofficial
    0.85
     unintentionally
    0.85
     incomplete
    0.85
    Act Density 0.163%

    No Known Activations