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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing preference or inclination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    754
    -0.16
    ady
    -0.15
    seau
    -0.15
    sein
    -0.14
    oui
    -0.14
    912
    -0.14
    finity
    -0.14
    oro
    -0.14
    VERR
    -0.14
    izu
    -0.13
    POSITIVE LOGITS
     to
    0.16
    igr
    0.15
    (exports
    0.15
     èIJ
    0.14
    utenberg
    0.14
     assistance
    0.14
    ardon
    0.13
    ToAdd
    0.13
    ordin
    0.13
    igious
    0.13
    Act Density 0.014%

    No Known Activations