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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating a lack of concern or care towards someone or something

    oai_token-act-pair · gpt-3.5-turbo

    discussions centered around indifference or lack of concern

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    arm
    -0.84
    Beta
    -0.80
    NAS
    -0.80
    cue
    -0.80
    DragonMagazine
    -0.78
    Cent
    -0.76
    Consider
    -0.75
    igmatic
    -0.74
    Sus
    -0.74
    auri
    -0.74
    POSITIVE LOGITS
     specifics
    1.06
     aesthetics
    1.05
     whether
    1.03
     politics
    1.02
     anything
    0.99
     winning
    0.98
     preserving
    0.98
     money
    0.97
     semantics
    0.95
     getting
    0.95
    Act Density 0.198%

    No Known Activations