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

    Neuronpedia

    INDEX
    Explanations

    words related to duties and responsibilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to duties and responsibilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     msec
    -0.66
    otide
    -0.65
    Cola
    -0.64
    ALLY
    -0.63
    ocent
    -0.61
    ILLE
    -0.61
     Kubrick
    -0.59
    jump
    -0.59
    allion
    -0.58
     paran
    -0.58
    POSITIVE LOGITS
    heet
    1.08
    pring
    0.95
    cape
    0.91
    afety
    0.91
     incurred
    0.90
    uits
    0.90
    hooting
    0.90
    hip
    0.89
    ibling
    0.85
     pertaining
    0.84
    Act Density 0.095%

    No Known Activations