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

    Neuronpedia

    INDEX
    Explanations

    words related to a specific direction, often indicating a negative connotation

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nai
    -0.76
    LU
    -0.75
    bians
    -0.74
    tein
    -0.73
    TL
    -0.70
    TED
    -0.69
    VA
    -0.66
    zb
    -0.66
    enos
    -0.66
    Prof
    -0.65
    POSITIVE LOGITS
     direction
    1.31
     directions
    1.22
    direction
    0.86
    finding
    0.85
    eering
    0.82
    naire
    0.77
     Direction
    0.76
    arity
    0.74
     alignment
    0.73
     orientation
    0.73
    Act Density 0.010%

    No Known Activations