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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate taking action or making progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    NSE
    -0.14
    ToolTip
    -0.14
    QRST
    -0.13
    amilia
    -0.13
    elas
    -0.13
     downwards
    -0.13
    _HS
    -0.13
    à¥ģà¤Ń
    -0.13
    endir
    -0.13
     पस
    -0.13
    POSITIVE LOGITS
     foot
    0.33
     aside
    0.30
     Foot
    0.23
    aside
    0.23
     FOOT
    0.23
     Aside
    0.21
     outside
    0.20
     things
    0.20
    Foot
    0.20
     ginger
    0.20
    Act Density 0.025%

    No Known Activations