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

    Neuronpedia

    INDEX
    Explanations

    punctuation marks indicating the end of statements or thoughts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     playbook
    -0.79
     locality
    -0.77
    icans
    -0.74
     specificity
    -0.72
    icum
    -0.72
     plain
    -0.69
    arious
    -0.69
    rams
    -0.66
    istas
    -0.65
    ellar
    -0.65
    POSITIVE LOGITS
    Continue
    0.84
    OVER
    0.82
    =>
    0.80
    Updated
    0.75
    Over
    0.75
    Join
    0.74
    Construction
    0.74
    GEN
    0.74
    Jordan
    0.74
    RFC
    0.73
    Act Density 0.500%

    No Known Activations