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

    Neuronpedia

    INDEX
    Explanations

    phrases related to weather phenomena, especially clouds

    oai_token-act-pair · gpt-3.5-turbo

    references to clouds, particularly in relation to ominous or negative contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -1.06
    thodox
    -0.81
    Home
    -0.73
    éĸ
    -0.73
    sembly
    -0.71
     Pwr
    -0.71
    ngth
    -0.71
    Union
    -0.70
    senal
    -0.69
    MIT
    -0.69
    POSITIVE LOGITS
    burst
    1.23
     clouds
    1.04
    bows
    0.95
     cloud
    0.94
     canopy
    0.89
    iness
    0.88
    flake
    0.88
    berries
    0.84
    arding
    0.82
     shroud
    0.82
    Act Density 0.014%

    No Known Activations