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

    Neuronpedia

    INDEX
    Explanations

    key roles and contributions of individuals in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    illet
    -0.17
    ovnÄĽ
    -0.15
    cola
    -0.15
    atoi
    -0.15
    positor
    -0.15
    udded
    -0.14
    udd
    -0.14
    ibly
    -0.14
    047
    -0.14
    ãĥ¼ãĥŃ
    -0.14
    POSITIVE LOGITS
     vis
    0.21
     towards
    0.20
    ings
    0.19
     toward
    0.19
     regarding
    0.17
     trav
    0.17
     concerning
    0.16
    ability
    0.16
     during
    0.16
    iness
    0.15
    Act Density 0.280%

    No Known Activations