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

    Neuronpedia

    INDEX
    Explanations

    words related to challenges or obstacles being faced or dealt with

    oai_token-act-pair · gpt-3.5-turbo

    references to "faces" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    RAFT
    -0.60
    Jump
    -0.60
     Mandatory
    -0.59
    ée
    -0.59
     remission
    -0.58
    oit
    -0.58
    ģ«
    -0.58
    rak
    -0.58
    mod
    -0.57
    piracy
    -0.56
    POSITIVE LOGITS
     faces
    4.09
     Faces
    2.66
     face
    2.41
    faces
    2.14
     faced
    1.75
     Face
    1.72
    face
    1.72
    Face
    1.71
     heads
    1.61
     mouths
    1.57
    Act Density 0.015%

    No Known Activations