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

    Neuronpedia

    INDEX
    Explanations

    phrases and words expressing the concept of influence across various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    nem
    -0.17
    ãģ¹ãģį
    -0.17
    isser
    -0.17
    itung
    -0.16
     Blasio
    -0.15
    ruba
    -0.15
    ish
    -0.15
    malink
    -0.14
    иÑī
    -0.14
    asaki
    -0.14
    POSITIVE LOGITS
    ively
    0.18
    uated
    0.17
    ãģ¨ãģĵãĤį
    0.16
    627
    0.16
    oft
    0.16
    iveness
    0.16
    /support
    0.15
    ential
    0.15
     jud
    0.15
    ìĤ¬íķŃ
    0.15
    Act Density 0.028%

    No Known Activations