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

    Neuronpedia

    INDEX
    Explanations

    mentions of individuals' names along with associated actions or comments

    oai_token-act-pair · gpt-3.5-turbo

    notifications or discussions regarding involvement or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    undown
    -0.79
     disadvant
    -0.74
     fortun
    -0.70
     guiActiveUnfocused
    -0.69
     adolesc
    -0.69
     fragmentation
    -0.68
     pressures
    -0.66
    odium
    -0.65
    ickets
    -0.65
     backdrop
    -0.64
    POSITIVE LOGITS
    swer
    0.87
    own
    0.86
    âĸł
    0.85
    audi
    0.84
    sure
    0.83
    ship
    0.81
    ··
    0.79
    must
    0.79
    else
    0.77
    âĸº
    0.76
    Act Density 0.117%

    No Known Activations