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

    Neuronpedia

    INDEX
    Explanations

    indicators of location or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Berger
    -0.16
     Fro
    -0.16
    chia
    -0.15
     diff
    -0.14
    CHAT
    -0.14
    acio
    -0.14
    ego
    -0.14
     CDDL
    -0.14
     poss
    -0.13
     dispos
    -0.13
    POSITIVE LOGITS
    .gs
    0.17
    uze
    0.16
    że
    0.14
    alara
    0.14
    tility
    0.14
    ÐIJÑĢÑħÑĸв
    0.14
    ylko
    0.13
    hek
    0.13
    -kind
    0.13
    -ÑĤо
    0.13
    Act Density 0.136%

    No Known Activations