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

    Neuronpedia

    INDEX
    Explanations

    commands related to toggling a feature or setting

    oai_token-act-pair · gpt-3.5-turbo

    commands related to toggling settings or options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Cav
    -0.71
     Schwe
    -0.69
    mort
    -0.67
    cert
    -0.66
     hom
    -0.64
     Cher
    -0.63
     Cater
    -0.61
     Ros
    -0.61
    rays
    -0.61
    bats
    -0.61
    POSITIVE LOGITS
     toggle
    3.78
    toggle
    2.36
    ggles
    1.96
     Toggle
    1.92
     switch
    1.25
    oggle
    1.15
     slider
    1.11
     tweak
    1.09
     mute
    1.09
    Enlarge
    1.07
    Act Density 0.010%

    No Known Activations