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

    Neuronpedia

    INDEX
    Explanations

    phrases related to taking action or making progress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     far
    -0.17
     FAR
    -0.17
    far
    -0.16
     anymore
    -0.15
    ao
    -0.15
    riad
    -0.15
     inf
    -0.14
     equally
    -0.14
    Far
    -0.14
    ulle
    -0.14
    POSITIVE LOGITS
     differently
    0.16
    ãĤĵãģ©
    0.16
    yna
    0.16
    nul
    0.15
    409
    0.15
    é£
    0.14
     parti
    0.14
    moth
    0.14
    eneg
    0.14
    /stdc
    0.14
    Act Density 0.043%

    No Known Activations