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

    Neuronpedia

    INDEX
    Explanations

    phrases expressing condition or speculation

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ©¶æ¥µ
    -0.82
    eteenth
    -0.68
     Whilst
    -0.67
    !.
    -0.65
    ibliography
    -0.64
    awan
    -0.64
    unless
    -0.63
    âĵĺ
    -0.63
    .:
    -0.62
    +.
    -0.62
    POSITIVE LOGITS
     sufficiently
    0.81
     anymore
    0.76
     somebody
    0.73
    ?",
    0.73
     something
    0.70
     somet
    0.69
     slightest
    0.69
     enough
    0.69
    ?,
    0.65
     tomorrow
    0.64
    Act Density 0.753%

    No Known Activations