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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate career progression and professional experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
    inton
    -0.15
    ntax
    -0.15
    andan
    -0.14
     subclass
    -0.14
    ylon
    -0.14
    .Atomic
    -0.14
     СÑĤÑĢана
    -0.14
    θεν
    -0.14
    lek
    -0.14
    OfClass
    -0.14
    POSITIVE LOGITS
     career
    0.53
     carrier
    0.45
     carr
    0.44
    career
    0.42
    -care
    0.40
     Carrier
    0.38
     carrera
    0.37
     careers
    0.36
     carriers
    0.36
    carrier
    0.35
    Act Density 0.079%

    No Known Activations