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

    Neuronpedia

    INDEX
    Explanations

    phrases related to mixing or combining elements together

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    uard
    -0.19
     Fra
    -0.14
    į°
    -0.14
    adora
    -0.14
    orz
    -0.14
    roje
    -0.13
    _NOTIFY
    -0.13
    reater
    -0.13
    SingleNode
    -0.13
    Guardar
    -0.13
    POSITIVE LOGITS
     thrown
    0.48
    thrown
    0.36
     throw
    0.33
    throw
    0.31
     included
    0.31
     added
    0.30
     Throw
    0.30
    Throw
    0.28
     threw
    0.28
     throws
    0.27
    Act Density 0.210%

    No Known Activations