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

    Neuronpedia

    INDEX
    Explanations

    text related to systems or structures that are based on specific criteria or principles

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating various types of "based" systems or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    someone
    -0.81
    some
    -0.79
    acious
    -0.79
    ilk
    -0.79
    irlf
    -0.76
    true
    -0.75
    recent
    -0.74
    atel
    -0.74
    avering
    -0.74
    osponsors
    -0.73
    POSITIVE LOGITS
    lihood
    0.84
     policing
    0.82
     enterprises
    0.80
     therapies
    0.80
     approach
    0.79
     shenanigans
    0.79
     interventions
    0.77
     initiatives
    0.77
     solutions
    0.76
     activities
    0.75
    Act Density 0.206%

    No Known Activations