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

    Neuronpedia

    INDEX
    Explanations

    conditional statements, particularly those that involve possibilities or hypothetical scenarios

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Pristupljeno
    -0.68
    SequentialGroup
    -0.61
    ValueStyle
    -0.61
    gives
    -0.58
     iprot
    -0.56
    umoj
    -0.55
     <<<<<<<<<<<<<<
    -0.55
    twimg
    -0.55
    ysis
    -0.55
    ERVE
    -0.54
    POSITIVE LOGITS
     überhaupt
    0.62
     Chwiliwch
    0.56
     ogóle
    0.49
     existent
    0.48
     paraître
    0.47
     existir
    0.46
    BeginContext
    0.45
    ActionCreators
    0.44
     вообще
    0.44
    是否存在
    0.42
    Act Density 0.249%

    No Known Activations