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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate actions or states of being, often associated with presence or engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    odel
    -0.16
    ode
    -0.15
    agal
    -0.15
    ứng
    -0.15
     alt
    -0.15
     Johns
    -0.15
    ddl
    -0.14
    .fc
    -0.14
    ussen
    -0.14
     Edmund
    -0.13
    POSITIVE LOGITS
    inel
    0.15
    .community
    0.15
    595
    0.14
    aÅŁ
    0.14
    Intl
    0.14
     zbo
    0.14
    lige
    0.14
    -aged
    0.14
    anlı
    0.14
    iatrics
    0.13
    Act Density 0.015%

    No Known Activations