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

    Neuronpedia

    INDEX
    Explanations

    commands or instructions initiating a specific action or discussion

    oai_token-act-pair · gpt-3.5-turbo

    commands or invitations to take action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Interstitial
    -0.72
    natureconservancy
    -0.71
     veins
    -0.60
    existent
    -0.60
     holiest
    -0.58
    ombat
    -0.56
     wielded
    -0.56
    cled
    -0.55
    creen
    -0.54
    born
    -0.54
    POSITIVE LOGITS
    itia
    0.93
    arations
    0.85
    tering
    0.84
    icia
    0.82
    tered
    0.82
     us
    0.81
    emort
    0.80
    ting
    0.79
    hetically
    0.77
     me
    0.71
    Act Density 0.021%

    No Known Activations