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

    Neuronpedia

    INDEX
    Explanations

    phrases related to progress or movement towards a goal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     AppModule
    -0.16
    akov
    -0.15
    uzzi
    -0.15
    skyt
    -0.15
    avl
    -0.15
    avra
    -0.14
    alta
    -0.14
    PTY
    -0.14
    Backing
    -0.14
    .scalablytyped
    -0.14
    POSITIVE LOGITS
     ahead
    0.89
     Ahead
    0.74
    ahead
    0.74
    Ahead
    0.67
    -ahead
    0.63
    head
    0.44
     head
    0.43
     впеÑĢед
    0.39
    HEAD
    0.37
     devant
    0.35
    Act Density 0.091%

    No Known Activations