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

    Neuronpedia

    INDEX
    Explanations

    verbs and adjectives related to social and political change

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and discussions about potential actions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Crazy
    -0.77
     Vista
    -0.71
    noticed
    -0.71
    Got
    -0.71
     Cortex
    -0.69
     Patty
    -0.65
     Tech
    -0.65
     logging
    -0.65
    76561
    -0.65
     checking
    -0.64
    POSITIVE LOGITS
     indeed
    1.19
     consist
    1.18
     arise
    1.18
     flourish
    1.15
     encompass
    1.13
     prevail
    1.13
     nevertheless
    1.12
     entail
    1.09
     suffice
    1.08
     scarcely
    1.07
    Act Density 0.238%

    No Known Activations