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

    Neuronpedia

    INDEX
    Explanations

    phrases related to political rhetoric and misinformation

    oai_token-act-pair · gpt-3.5-turbo

    statements about misconceptions and myths regarding bisexuality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    hess
    -0.69
     Grateful
    -0.66
    ktop
    -0.62
    atra
    -0.62
     contrace
    -0.62
    atri
    -0.61
    foreseen
    -0.61
    sung
    -0.60
     Rhythm
    -0.60
    syn
    -0.60
    POSITIVE LOGITS
     falsely
    0.90
     excuses
    0.89
     nonsense
    0.87
     justification
    0.85
     ignorance
    0.85
     ignor
    0.85
     scapego
    0.84
     delusions
    0.83
     baseless
    0.83
     slander
    0.81
    Act Density 0.691%

    No Known Activations