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

    Neuronpedia

    INDEX
    Explanations

    phrases that emphasize the importance of processes and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    thinkable
    -0.16
    _CAST
    -0.15
     lô
    -0.14
    cox
    -0.14
    loquent
    -0.14
    ignet
    -0.14
    ilis
    -0.14
    fh
    -0.14
    isse
    -0.13
    rone
    -0.13
    POSITIVE LOGITS
     critical
    0.41
    critical
    0.34
     vit
    0.34
     Critical
    0.32
     vital
    0.32
     fundamental
    0.32
     krit
    0.30
     central
    0.30
     critically
    0.29
    Critical
    0.28
    Act Density 0.130%

    No Known Activations