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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the conclusion or final details in a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     /
    -0.19
    aylor
    -0.17
    751
    -0.17
    967
    -0.15
    loor
    -0.14
     adherence
    -0.14
    conte
    -0.14
     Aure
    -0.14
    531
    -0.14
     conce
    -0.14
    POSITIVE LOGITS
    otta
    0.16
    esc
    0.16
    armor
    0.15
    uctor
    0.14
    addy
    0.14
    UniqueId
    0.14
    ानम
    0.14
    ombat
    0.14
    DCALL
    0.14
    blick
    0.14
    Act Density 0.026%

    No Known Activations