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

    Neuronpedia

    INDEX
    Explanations

    phrases related to directional changes or transformations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     tableau
    -0.47
    prio
    -0.43
     estu
    -0.42
    UrlResolution
    -0.42
    merk
    -0.41
     financiers
    -0.41
    Molto
    -0.41
    luence
    -0.41
     verz
    -0.40
     exploded
    -0.40
    POSITIVE LOGITS
    turn
    0.93
    Turn
    0.89
     turn
    0.89
     turns
    0.84
     Turn
    0.82
    TURN
    0.82
     TURN
    0.79
    turns
    0.79
    Turns
    0.68
    Turned
    0.68
    Act Density 0.397%

    No Known Activations