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

    Neuronpedia

    INDEX
    Explanations

    phrases related to approaching events or actions

    oai_token-act-pair · gpt-3.5-turbo

    words related to time-related actions and transitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arta
    -0.76
     stances
    -0.74
    è¦ļéĨĴ
    -0.74
     defends
    -0.73
    tein
    -0.69
    archives
    -0.65
     retains
    -0.65
     Parables
    -0.64
     defended
    -0.61
     lengths
    -0.61
    POSITIVE LOGITS
     bitters
    0.70
    mAh
    0.69
     Brett
    0.68
     evapor
    0.68
    orescence
    0.66
     Rosenberg
    0.65
     mell
    0.65
     exhausted
    0.65
     exhaustion
    0.64
     blurry
    0.64
    Act Density 0.972%

    No Known Activations