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

    Neuronpedia

    INDEX
    Explanations

    words related to dependencies or factors influencing outcomes

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "depend" and its variations, indicating factors or conditions that influence outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    vision
    -0.80
    ãĥīãĥ©
    -0.71
    anas
    -0.67
    ãĥ´
    -0.66
    unci
    -0.64
    ãĥ«
    -0.64
    ãģĦ
    -0.64
    ãĥŃ
    -0.64
    nik
    -0.63
    sell
    -0.62
    POSITIVE LOGITS
     upon
    0.98
    ants
    0.86
    ymm
    0.84
     critically
    0.81
     heavily
    0.80
    ancy
    0.80
     solely
    0.80
    ocre
    0.74
    ancies
    0.74
    edIn
    0.73
    Act Density 0.020%

    No Known Activations