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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating personal opinion or judgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinion or perspective

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Uriel
    -0.77
    trump
    -0.71
    ress
    -0.69
    yip
    -0.68
    irds
    -0.67
    letes
    -0.66
    onto
    -0.65
    orthy
    -0.65
    oline
    -0.65
    lete
    -0.65
    POSITIVE LOGITS
     estimation
    1.34
     opinion
    1.21
     absence
    1.10
     case
    1.08
     sense
    1.07
     midst
    1.05
     view
    1.04
     dealings
    0.98
     haste
    0.98
     eyes
    0.98
    Act Density 0.083%

    No Known Activations