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

    Neuronpedia

    INDEX
    Explanations

    words related to strong interests or fixations

    oai_token-act-pair · gpt-3.5-turbo

    terms related to intense fixation or preoccupation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ģ«
    -0.67
     Equality
    -0.65
    Medic
    -0.65
    stood
    -0.64
    stand
    -0.62
    neau
    -0.60
     degradation
    -0.60
    gs
    -0.60
    izontal
    -0.60
    GG
    -0.59
    POSITIVE LOGITS
    ishly
    0.89
     fascination
    0.87
    iously
    0.80
     obs
    0.80
     fascinated
    0.78
    MJ
    0.75
    meric
    0.73
     obsession
    0.72
    atically
    0.72
     obsess
    0.72
    Act Density 0.070%

    No Known Activations