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

    Neuronpedia

    INDEX
    Explanations

    references to projects or services

    oai_token-act-pair · gpt-3.5-turbo

    words related to projects and supporting community initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    pload
    -0.68
     incorpor
    -0.63
     Schro
    -0.60
    itialized
    -0.60
    udos
    -0.56
    TABLE
    -0.56
     omission
    -0.54
     reconc
    -0.53
     retract
    -0.50
     explan
    -0.50
    POSITIVE LOGITS
    .
    0.88
    .</
    0.87
    *.
    0.84
    .:
    0.83
     or
    0.81
    .''.
    0.81
    .*
    0.78
     anymore
    0.77
    .''
    0.77
    _.
    0.74
    Act Density 0.678%

    No Known Activations