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

    Neuronpedia

    INDEX
    Explanations

    action or movement-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    اÙĨÙĬØ©
    -0.17
    .Invariant
    -0.15
    sein
    -0.15
    dfs
    -0.15
    abus
    -0.14
    ampions
    -0.14
    驾
    -0.14
    ilded
    -0.14
     onward
    -0.14
    uchos
    -0.14
    POSITIVE LOGITS
     towards
    0.21
     toward
    0.21
    _DEFINE
    0.15
    Towards
    0.15
     away
    0.14
     past
    0.14
     Towards
    0.14
    gli
    0.14
    564
    0.14
     step
    0.14
    Act Density 0.022%

    No Known Activations