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

    Neuronpedia

    INDEX
    Explanations

    pronouns and personal references in relation to actions and decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    noinspection
    -0.15
    unes
    -0.15
     Haut
    -0.14
    undry
    -0.14
     Hawkins
    -0.14
    emale
    -0.14
     schö
    -0.14
    ambia
    -0.14
     Org
    -0.14
    unto
    -0.14
    POSITIVE LOGITS
    éĻ½
    0.16
    uada
    0.16
    CCC
    0.15
     gro
    0.15
    fs
    0.14
     Titan
    0.14
    itom
    0.14
    Äįen
    0.14
    utsch
    0.14
    stretch
    0.14
    Act Density 0.485%

    No Known Activations