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

    Neuronpedia

    INDEX
    Explanations

    phrases related to physical and emotional suffering or deprivation

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "nes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ivation
    -0.80
    arna
    -0.72
    atories
    -0.70
    rador
    -0.68
    masters
    -0.67
    irlf
    -0.65
    ivating
    -0.64
    rament
    -0.64
    izoph
    -0.63
    boards
    -0.63
    POSITIVE LOGITS
    earch
    0.98
    ville
    0.94
    nes
    0.94
    cape
    0.89
    boro
    0.88
    creen
    0.86
    erve
    0.86
    forth
    0.84
    esis
    0.84
    burgh
    0.82
    Act Density 0.014%

    No Known Activations