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

    Neuronpedia

    INDEX
    Explanations

    words related to metabolic processes or physical states

    oai_token-act-pair · gpt-3.5-turbo

    words related to physical or abstract measurements and metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    Ô
    -0.82
     ankles
    -0.68
     situational
    -0.67
    birth
    -0.66
     allowances
    -0.65
    ples
    -0.64
    mington
    -0.64
     unpaid
    -0.60
    gged
    -0.59
    ammy
    -0.57
    POSITIVE LOGITS
    eering
    0.98
    eers
    0.93
    opia
    0.86
    andum
    0.84
    istan
    0.83
    rophe
    0.82
    ectomy
    0.81
    ensis
    0.79
    ronics
    0.78
    algia
    0.78
    Act Density 0.132%

    No Known Activations