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

    Neuronpedia

    INDEX
    Explanations

    cases where something is left to happen or be unresolved

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to abandonment or being left behind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ML
    -0.71
    enos
    -0.68
    TX
    -0.60
     conversions
    -0.60
    ulse
    -0.60
     fasc
    -0.59
    lies
    -0.59
    frey
    -0.58
    interstitial
    -0.57
    phony
    -0.57
    POSITIVE LOGITS
     untreated
    0.87
     unanswered
    0.85
     voic
    0.81
     alone
    0.77
     rot
    0.75
     untouched
    0.73
    stal
    0.73
     unresolved
    0.71
    OGR
    0.71
    whel
    0.70
    Act Density 0.134%

    No Known Activations