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

    Neuronpedia

    INDEX
    Explanations

    phrases or constructs indicating a state or condition that involves being 'on.'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    rij
    -0.16
    ifa
    -0.15
    ote
    -0.15
    xAA
    -0.15
    _iff
    -0.14
    agan
    -0.14
    .EventType
    -0.14
    ween
    -0.14
    olina
    -0.13
     sclerosis
    -0.13
    POSITIVE LOGITS
     leave
    0.21
     duty
    0.20
     holiday
    0.19
     vacation
    0.19
     jury
    0.18
     hiatus
    0.18
    leave
    0.17
     strike
    0.17
     quests
    0.17
     trial
    0.17
    Act Density 0.087%

    No Known Activations