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

    Neuronpedia

    INDEX
    Explanations

    references to sexuality

    oai_token-act-pair · gpt-3.5-turbo

    references to sexuality and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    MER
    -0.74
    gran
    -0.70
    ×Ļ×
    -0.66
    Ing
    -0.66
    abet
    -0.65
    kson
    -0.63
    ACTED
    -0.63
    VIS
    -0.63
    Trust
    -0.62
    ioxide
    -0.62
    POSITIVE LOGITS
    uality
    1.00
     sexuality
    0.99
    nesday
    0.98
    creen
    0.84
    isphere
    0.77
    apore
    0.75
     offend
    0.74
     spectrum
    0.71
    oking
    0.71
     attracted
    0.67
    Act Density 0.016%

    No Known Activations