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

    Neuronpedia

    INDEX
    Explanations

    ellipsis points (…) at the end of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    ellipsis or pauses in the text, indicating an ongoing thought or continuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     prosperity
    -0.74
     depletion
    -0.71
     cohesion
    -0.71
     oxide
    -0.71
     flourish
    -0.70
     prominence
    -0.69
     clashed
    -0.69
     misfortune
    -0.69
     antip
    -0.69
     rebell
    -0.68
    POSITIVE LOGITS
    BUT
    1.17
    until
    1.11
    except
    1.01
    among
    1.00
    yet
    1.00
    unless
    0.94
    but
    0.93
    why
    0.92
    they
    0.91
     âĢİ
    0.91
    Act Density 0.048%

    No Known Activations