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

    Neuronpedia

    INDEX
    Explanations

    references to natural environments like wilderness

    oai_token-act-pair · gpt-3.5-turbo

    references to wilderness or natural environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    abolic
    -0.74
    odor
    -0.71
    akin
    -0.71
    eon
    -0.69
    abol
    -0.67
    orah
    -0.67
    rupulous
    -0.67
    Americans
    -0.67
    mus
    -0.65
    sei
    -0.64
    POSITIVE LOGITS
     wilderness
    1.19
    erness
    1.13
     Wilderness
    1.06
     wasteland
    0.88
    ocene
    0.88
     paradise
    0.81
     frontier
    0.80
    pedia
    0.75
     Survival
    0.75
     jungle
    0.75
    Act Density 0.006%

    No Known Activations