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

    Neuronpedia

    INDEX
    Explanations

    statements of support or opposition for various topics or causes

    oai_token-act-pair · gpt-3.5-turbo

    expressions of support or endorsement for various issues or causes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ngth
    -0.73
     proble
    -0.72
    iae
    -0.71
     nerv
    -0.69
     teasp
    -0.68
    terness
    -0.68
    ixtape
    -0.67
    vity
    -0.67
     mismatch
    -0.66
    atonin
    -0.66
    POSITIVE LOGITS
    enance
    0.78
     uncond
    0.76
     arming
    0.76
     endorsing
    0.74
     legalizing
    0.74
     reelection
    0.73
     whichever
    0.72
    Support
    0.72
    roud
    0.71
     adoption
    0.71
    Act Density 0.101%

    No Known Activations