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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating the provision or generation of support or resources

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    éĺ
    -0.17
     RESERVED
    -0.15
    Fluid
    -0.15
    ä»ķ
    -0.14
    Gesture
    -0.14
    vi
    -0.13
    frag
    -0.13
     ----------------------------------------------------------------------------------------------------------------
    -0.13
    avors
    -0.13
    ieber
    -0.13
    POSITIVE LOGITS
     pause
    0.35
     ammunition
    0.29
     cause
    0.28
     fuel
    0.26
     ammo
    0.26
     Pause
    0.25
     reason
    0.25
    pause
    0.24
     grounds
    0.24
     sol
    0.23
    Act Density 0.165%

    No Known Activations