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

    Neuronpedia

    INDEX
    Explanations

    sentences that describe or evaluate a particular subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    867
    -0.16
    arella
    -0.15
    865
    -0.15
    appy
    -0.15
    èŃ°
    -0.14
    odos
    -0.14
    áh
    -0.14
    otle
    -0.14
    aterno
    -0.14
    acula
    -0.13
    POSITIVE LOGITS
     part
    0.27
     Part
    0.26
     dedicated
    0.19
    _part
    0.19
     dedicate
    0.19
    Part
    0.19
     brought
    0.18
     courtesy
    0.17
     excerpt
    0.17
     parte
    0.17
    Act Density 0.110%

    No Known Activations