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

    Neuronpedia

    INDEX
    Explanations

    words related to physical destruction or deliberate damage

    oai_token-act-pair · gpt-3.5-turbo

    words related to actions or states of being that imply change or transition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    enegger
    -0.88
    jen
    -0.82
    lander
    -0.81
    ruary
    -0.72
    overe
    -0.71
    agar
    -0.70
    owa
    -0.69
    land
    -0.68
    LAND
    -0.68
    enhagen
    -0.66
    POSITIVE LOGITS
    anism
    0.68
    uries
    0.65
    rogram
    0.65
    onite
    0.63
    ictions
    0.63
    otomy
    0.61
    epad
    0.61
     arsen
    0.61
     circuitry
    0.59
     wire
    0.59
    Act Density 0.096%

    No Known Activations