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

    Neuronpedia

    INDEX
    Explanations

    adjectives related to possible actions or qualities

    oai_token-act-pair · gpt-3.5-turbo

    words related to fulfillment or successful actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ernels
    -0.77
    Downloadha
    -0.77
    ivari
    -0.76
    ISC
    -0.71
    IRO
    -0.70
    atform
    -0.69
    ocl
    -0.69
    ribe
    -0.69
    æ©
    -0.69
    CHAT
    -0.68
    POSITIVE LOGITS
    theless
    0.96
     ignorance
    0.81
     glances
    0.76
    NESS
    0.76
    terday
    0.76
     idiots
    0.75
    tarian
    0.74
    filled
    0.73
    Appearances
    0.71
    vous
    0.70
    Act Density 0.071%

    No Known Activations