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

    Neuronpedia

    INDEX
    Explanations

    words related to guidance or control

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    en
    -0.16
    lias
    -0.16
    ocs
    -0.15
    iad
    -0.15
    pire
    -0.15
     stretch
    -0.15
     guilt
    -0.15
    Ìģt
    -0.14
    oken
    -0.14
     frank
    -0.14
    POSITIVE LOGITS
    shint
    0.15
     же
    0.14
    orrent
    0.14
    tee
    0.14
    -direct
    0.14
    /control
    0.14
    tees
    0.13
    èĩ´
    0.13
     Gareth
    0.13
    memberOf
    0.13
    Act Density 0.026%

    No Known Activations