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

    Neuronpedia

    INDEX
    Explanations

    phrases related to deep understanding or insight

    oai_token-act-pair · gpt-3.5-turbo

    end punctuation and quotation marks used in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     mur
    -0.43
    anka
    -0.43
    natureconservancy
    -0.43
     quir
    -0.39
     politic
    -0.39
     brill
    -0.39
     bre
    -0.38
     fuss
    -0.38
    sted
    -0.38
    ciplinary
    -0.37
    POSITIVE LOGITS
    swick
    0.58
     Needless
    0.56
     Alternatively
    0.53
     Additionally
    0.49
    anwhile
    0.49
     Lastly
    0.49
     Conversely
    0.48
    arsity
    0.47
    ONSORED
    0.47
    evidence
    0.47
    Act Density 1.039%

    No Known Activations