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

    Neuronpedia

    INDEX
    Explanations

    instances of the word "look" in various forms, indicating a focus on expressions of anticipation or interest

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uali
    -0.18
    æĤł
    -0.16
    ooth
    -0.16
    haven
    -0.15
    otta
    -0.15
    _LEG
    -0.15
     Gol
    -0.14
    occo
    -0.14
     åħ«
    -0.14
    EMPLARY
    -0.14
    POSITIVE LOGITS
     forward
    0.46
    forward
    0.31
    -forward
    0.27
     fwd
    0.27
     FORWARD
    0.27
     forwarding
    0.27
     forwarded
    0.26
    .forward
    0.26
    _forward
    0.26
     f
    0.24
    Act Density 0.013%

    No Known Activations