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

    Neuronpedia

    INDEX
    Explanations

    phrases that involve future events or anticipated outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    _INTR
    -0.14
    harma
    -0.14
     Davidson
    -0.14
    UNS
    -0.14
    WINDOWS
    -0.13
    ilim
    -0.13
    metro
    -0.13
    panse
    -0.13
    oplan
    -0.13
     heartbeat
    -0.13
    POSITIVE LOGITS
    anka
    0.18
    illow
    0.17
    heim
    0.17
    iale
    0.16
    eka
    0.16
    rig
    0.15
    furt
    0.15
    вай
    0.15
    imir
    0.15
    joy
    0.15
    Act Density 0.177%

    No Known Activations