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

    Neuronpedia

    INDEX
    Explanations

    phrases and structures related to actions and positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    åº
    -0.73
    Introduced
    -0.67
    verage
    -0.65
    represented
    -0.65
    ADVERTISEMENT
    -0.64
    DragonMagazine
    -0.64
    anches
    -0.63
    ilings
    -0.63
    acca
    -0.63
    Posted
    -0.62
    POSITIVE LOGITS
     raining
    0.83
     myself
    0.77
    Ħ¢
    0.74
     yourself
    0.73
     anyway
    0.73
    washer
    0.71
     ourselves
    0.71
     anyways
    0.69
    alone
    0.67
     funny
    0.63
    Act Density 0.181%

    No Known Activations