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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating sequences of events or prior conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    ValueStyle
    -0.77
     Италијани
    -0.62
    IsMutable
    -0.60
     utafitiHapana
    -0.54
     OMITBAD
    -0.54
    __(/*!
    -0.53
    aarrggbb
    -0.52
     Infórmanos
    -0.52
     consequent
    -0.52
     IFTT
    -0.51
    POSITIVE LOGITS
    Before
    0.92
     Before
    0.91
     before
    0.75
     sebelum
    0.72
    Antes
    0.69
    Sebelum
    0.69
     ennen
    0.68
    before
    0.67
     antes
    0.65
     BEFORE
    0.63
    Act Density 0.015%

    No Known Activations