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

    Neuronpedia

    INDEX
    Explanations

    action verbs in the past tense

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe processes of creation and continuity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    heads
    -0.70
    è£ħ
    -0.69
    é¾į
    -0.67
    å°Ĩ
    -0.66
    ilings
    -0.66
    TP
    -0.64
    OTA
    -0.64
    avid
    -0.64
    ctors
    -0.63
    ourse
    -0.63
    POSITIVE LOGITS
     raining
    1.44
     downhill
    0.78
     itself
    0.72
     happen
    0.71
    lit
    0.69
     cheaper
    0.68
     anyway
    0.67
    chy
    0.67
     easier
    0.66
     uphill
    0.66
    Act Density 0.615%

    No Known Activations