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

    Neuronpedia

    INDEX
    Explanations

    mentions of physical settings or locations

    oai_token-act-pair · gpt-3.5-turbo

    elements and descriptors related to nature and the environment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Accountability
    -0.74
    Policy
    -0.68
    olicy
    -0.65
     Disclosure
    -0.64
     Sponsor
    -0.63
     Opinion
    -0.63
    endment
    -0.62
    uthor
    -0.62
     Nationwide
    -0.61
    Asset
    -0.61
    POSITIVE LOGITS
     hypnot
    0.63
     vines
    0.63
     tubes
    0.61
     bushes
    0.61
     ecstasy
    0.59
     throb
    0.59
     protr
    0.58
     nause
    0.58
     needles
    0.58
     enchanted
    0.57
    Act Density 3.587%

    No Known Activations