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

    Neuronpedia

    INDEX
    Explanations

    phrases related to opinions and subjective evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    orrent
    -0.16
    chez
    -0.15
    silver
    -0.15
    eres
    -0.15
    _ops
    -0.14
    eç
    -0.14
    rieving
    -0.14
    erken
    -0.14
    yre
    -0.14
    515
    -0.14
    POSITIVE LOGITS
    inion
    0.44
    inions
    0.42
    portunity
    0.38
    port
    0.32
    portun
    0.31
    ener
    0.26
    PORT
    0.25
    ponent
    0.23
    ponents
    0.23
    posite
    0.22
    Act Density 0.009%

    No Known Activations