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

    Neuronpedia

    INDEX
    Explanations

    phrases related to critique or dissent

    oai_token-act-pair · gpt-3.5-turbo

    statements about policies and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    OTUS
    -0.70
    rex
    -0.68
    ozo
    -0.67
    Tonight
    -0.65
    said
    -0.64
    eon
    -0.64
    daq
    -0.63
    estern
    -0.62
    obbies
    -0.60
    Pict
    -0.60
    POSITIVE LOGITS
     unfairly
    1.25
     improperly
    0.93
     mishand
    0.89
     unfair
    0.87
     flawed
    0.87
     violates
    0.86
     inappropriately
    0.85
     insufficient
    0.85
     inadequate
    0.81
     violated
    0.81
    Act Density 0.463%

    No Known Activations